Showing 14 results for Logistic Regression
Volume 1, Issue 2 (6-2013)
Abstract
Logistic regression (LR) was used to model urban growth between the years 1987 and 2001 in Gorgan city, north east of Iran. Three groups of variables including economic-social, land use and biophysical variables were used in the modeling practice. Using covariance of the independent variables, distance to administrative and sporting centers plus distance to cities were removed. ROC (Relative Operating Characteristic) value for LR was 0.87 that confirmed success of the modeling method. Using maps of urban growth probability predicted by the LR model, urban distribution patterns for the years 2010, 2020, 2030, 2040 and 2050 were created. Land use maps for the years 2001-2050 were created using urban probability pattern maps and the base land use map of the year 1987. We used landscape metrics at class and landscape levels to compare the urban growth effects on other land use types present in the area. The comparison showed that urban development influences agriculture and pasture land use types more than other land uses. Also, we found that the landscape in the study area has undergone fragmentation and will become more fragmented and heterogeneous over time. Urban growth creates higher urban patchiness and increases the number of pasture and agricultural patches. The information thus obtained is helpful in more effective management of the area.
Volume 1, Issue 2 (2-2009)
Abstract
The identity of a society is a tool for distinguishing different nations from each other based on a common concept or predetermined concepts. The strong sense of identity can be considered as a social capital. In addition, social capital and social identity are the result of tangible social relationships, which are understandable by the society. They Also have strong affects on each other. With respect to this relationship, this paper verifies the relationship between identity and social capital. The data were gathered from the world values data of 70 countries according to the definitions of the variables. The results by logistic regression showed that there is a positive and significant relationship between social identity and social capital.
Volume 10, Issue 3 (8-2024)
Abstract
Background: The escalating prevalence of multidrug-resistant (MDR) commensal intestinal bacteria characterized by extended-spectrum β-lactamase (ESBL) production is an alarming global health threat. Drug users have been introduced as a major source of antibiotic-resistant bacteria, possibly due to drug abuse. The present study aimed to investigate the potential factors related to fecal carriage of MDR ESBL-producing intestinal Escherichia coli (E. coli) in drug users in the southwest of Iran.
Materials & Methods: In this cross-sectional study, stool samples of 109 drug users were collected and cultured. After the biochemical confirmation of E. coli isolates, the antimicrobial resistance pattern and ESBL production of the isolates were determined. Then logistic regression analysis was conducted to determine possible factors related to fecal carriage of MDR ESBL-producing intestinal E. coli.
Findings: Logistic regression analysis indicated that increasing age and duration of addiction were associated with increased risk of MDR ESBL-producing E. coli carriage in the intestinal flora of drug users (p< .05). Moreover, oral drug use compared to the smoking method led to a higher carriage rate of MDR ESBL-producing E. coli in the intestinal flora of drug users (p< .05). Also, self-employed drug users compared to those with fixed public occupation showed higher rates of MDR ESBL-producing E. coli carriage in their intestinal flora (p< .05).
Conclusion: Age, duration of addiction, method of drug use, and occupation were significantly associated with MDR ESBL-producing E. coli colonization.
Mohammad Rahim Ramazanian, Akram Oveysi Omran, Keykhosrow Yakideh,
Volume 14, Issue 3 (9-2014)
Abstract
Banks play substantial role in the national economy and its growth and prosperity. In this regard, recent researches have focused on performance evaluation of banks using “data envelopment analysis” (DEA). However, most of these studies has paid less attention to the selection of input and output variables. Obviously, the change in the variables set makes the efficiency scores and assessments of the decision-making units very different. Hence, in this paper, a logistic regression model is used in order to select the input and output variables. Applying this method indicates that the main variables of model are main source of financing as "input variable" and the bank facilities, resource absorption rate and number of bills as "output variables". These are of the greatest impact on forecasting of units efficiency (inefficiency). Then, we dealt with this set of variables to determine technical, allocative, and overall efficiency of 15 branches of Sepah Bank in Tehran during 2011. The results show that only 27 percent of units are 100% efficient, 20% of the units are 100% inefficient, 20% of units are allocatively inefficient and 34% of them are technically inefficient.
Nasser Jamshidi, Gholamreza Jandaghi, Reza Tehrani,
Volume 14, Issue 3 (9-2014)
Abstract
This paper examines and models the causes of deferring repayments in Qarz Al-Hasaneh Mehr Bank (QMB) of Iran. In the model, the effects of explanatory variables, including “kind of caught guaranty from customers”, “value of caught guaranty”, “kind of facilities”, “duration of repayment” and “amount of facilities”, on dependent variable “ deferring repayment of facilities” are investigated. In this research, the statistical population consists of customers of QMB branches in Tehran provinces during 2007-2011, which was selected by cluster sampling. For modeling causes of deferring repayments, both logistic regression and discrimination analysis were used and data was analyzed with SPSS software. According to the results of research, both models were significant, but logistic regression model was more robust in predicting probability of deferring repayment of granted facilities, so that, it predicted 84.5% of deferred facilities and 54% of repaid facilities, correctly. In addition, “the kind of guaranty” (cheque and payroll deduction authorization) and “kind of facilities” have negative and positive impact on deferring repayments, respectively.
Volume 15, Issue 3 (11-2011)
Abstract
The Assessment of Financial Distress in Tehran Stock Exchange: A Comparative Study
Between Data Envelopment Analysis
(DEA) and Logistic Regression (LR)
Mohammad Reza Rostami1, Mirfeyz Fallahshams2,
Farzaneh Eskandari3
1- Assistant Professor, Department of Management, Faculty of Social Sciences & Economics, Alzahra University, Tehran, Iran
2- Associate Professor, Department of Management, Faculty of Social Sciences & Economics, Alzahra University, Tehran, Iran
3- Msc., Department of Management, Faculty of Social Sciences & Economics, Alzahra University, Tehran, Iran
Received: 5 /9/2010 Accept: 13/8/2011
Financial distress evaluation is important because firm failure imposes significant direct and indirect costs on a firm’s stakeholders. Hence, using financial ratios has been considered by bank loan officers, creditors, stockholders, financial analysts, and the general public in order to provide them with timely and accurate assessment.
Timely evaluation can help decision makers to find the optimal way and predict bankruptcy. There are different models for financial distress evaluation, which are mainly applied in decision making by financial market players. It has been attempted to improve the accuracy of these models by more developed techniques.
The main goal of this research is to examine the capability of the additive model of Data Envelopment Analysis (DEA) model in assessing corporate financial distress by comparing it with logistic regression (LR). The results showed that in within-sample evaluation, LR outperforms DEA (Additive model) in correctly identifying the default firms significantly.
Volume 16, Issue 6 (11-2014)
Abstract
The extensive use of traditional irrigation systems has led to overexploitation of groundwater and overuse of surface water in theUrmia Lake Catchment (ULC) area ofIran. The purpose of this study was to model the adoption process of drip irrigation system (DIS) by apple orchardists (AOs) using the five stages of Roger’s model for Innovation Decision Process (IDP). Survey method of applying questionnaire and interview technique was used to collect data from 136 AOs. The results of the study indicated that, first, AOs’ knowledge level was “relatively low” and the majority of them were in the early stages of IDP. Secondly, applying an ordinal logistic regression, up to 36.3% of knowledge level variability, could be explained by variables consisting of: the contact level with extension agents, educational level, rural-urban commuting and information sources. Thirdly, using binary logistic regression, up to 74.1% of probability of adoption, could be explained by variables consisting of source of irrigation, knowledge scores, and orchard size. Fourthly, the main barriers for adoption were high costs, lack of license for semi deep wells, need to grow alfalfa, poor knowledge, and low surface area, respectively. Fifthly, about 0.5% of AOs had already implemented DIS. These findings were instrumental for localizing a model and developing the needed policy and institutional interventions falfa, poor knowledge, and low surface area, respectively. Fifthly, about 0.5% of AOs had already implemented DIS. These findings were instrumental for localizing a model and developing the needed policy and institutional interventions.
Volume 19, Issue 1 (1-2017)
Abstract
Canola production is an important alternative for agricultural policy-makers in Iran to reduce dependency on the imported vegetable oils. Nevertheless, the canola planted area is only increasing at a slow pace, indicating a low willingness-to-accept of farmers. The general aim of this study was to determine the factors influencing the canola adoption in the Kermanshah Province in Western Iran. Employing stratified random sampling method, 106 farmers from each adopter and non-adopter group were selected. Helping to reach a suitable extensional program, two main categories of variables were defined; i.e. “farmers’ personal characteristics” and “extension parameters”. The analysis of farmers’ personal characteristics variables revealed that the adopters had larger farms and were younger. The results also show that 80% of the adopters were “highly” to “very highly” willing to cultivate canola. Furthermore, a logistic regression model estimated the influence of extensional parameters variables on the canola adoption. According to the regression model, the most effective factors are “contact with extension agents” and “participating in extension classes”. As a conclusion, it is suggested that the focus of extension services should be to reduce the distance to agricultural service centers in combination with more contact with extension agents and classes.
Volume 19, Issue 3 (5-2017)
Abstract
The purpose of this study was to determine the socio-economic and intellectual factors affecting the imported meat preferences of consumers and to reveal the personal prioritized preferences of buyers consuming domestic meat and imported meat. The study was carried out in Izmir, the third city of Turkey, where face-to-face interviews were conducted in 300householdswhose occupants shop at hypermarkets where domestic and imported meat is sold. 28.7% of those participating in the study prefer imported meat. As a result of logistic regression, the approach related to the share of cattle meat in the total meat spend, the age factor and the belief that the price of imported cattle meat is low positively affect the probability of consuming imported meat. The consumption of chicken and lamb and marital status has negative effects. The religious belief factor and the perception of taste in those consuming imported meat take priority in the personal preferences of domestic meat consumers. Long-term policies that will ensure stability in the market as a whole are needed in the livestock sector in Turkey. Improvement of meat quality, classification and the rising awareness of consumers regarding quality and farming according to nutritional requirements and the development of certification also have significant importance.
Volume 19, Issue 4 (1-2016)
Abstract
Land use and land cover change has become an important problem in many countries. These changes have direct impacts on component of environment like soil, water and atmosphere and land use changes are key elements in studying global environmental changes. Modeling and simulation of land use changes have an important role in resources management and helps managers to better planning of land use. This research firstly investigated the synthetic method of land use classification in the Ramian city, South of Golestan province. Then land use change between years 2000 and 2012 was determined using remote sensing technique. Land use demand calculated using extrapolating past changes of land use. The rule of effective factors on land use was investigated using logistic regression. Finally land use patterns in Ramian was simulated for the year 2030 from the actual land use data for the year 2000 and the year 2012, respectively, by spatial land allocation of CLUE-s model. The results showed that synthetic classification is a suitable method to prepare land use map. Our findings also showed that the main land use changes in Ramian were the conversion of forest and rangeland areas to agriculture and residential land. Effective information regarding future land use provides useful tools for decision making in land use planning, management and policies.
Volume 23, Issue 1 (5-2019)
Abstract
Today, a wide range of spatial analysis models are used in environmental risk zoning. Some models, such as hierarchical and fuzzy analyzes, despite the inclusion of uncertainty in the input variables, are unable to explain quantitatively the output uncertainty. In this study, the aim of evaluating the capabilities of the Dempster-Schaeffer algorithm is to explain the uncertainty in the outcomes for landslide hazard zonation in the south of Chalus. Therefore, after field studies and review of similar studies, a map of 10 factors was provided in the GIS environment and was introduced as input data along with a map of the distribution of landslides to the model. Landslide hazard zonation was performed by integrating different weights in the Dempster-Sheffer model and in order to evaluate the output of the model, a logistic regression model was used; the performance of the two models was based on the output results of the models and using two indicators of the density ratio (Dr) And the sum of utility (Qs) was evaluated and verified. The results of Dr showed that both models had good performance in identifying high-risk classes compared to low risk classes. Based on the Qs index, the Dempster-Schafer model with QS = 98/2 was good compared to Logistic regression model with QS = 91/66 has a better relative utility. Therefore, the D-S model is more successful in identifying risk classes (finiteness) and consequently hazard classes (uncertainty) in the region.
Volume 23, Issue 1 (5-2019)
Abstract
Urban physical growth is affected by different parameters including environmental, neighborhood and socio-economic factors; however, socio-economic variables are often ignored due to the lack of socio-economic information, especially in developing countries, when the urban physical growth analysis and modeling is the aim. Accordingly, there is not many studies conducted to develop GIS-based socio-economic layers to be used along with common data, such as slope, distance to the roads and so on, in urban physical growth modeling. Therefore, this study aims to introduce an efficient method to generate GIS-based socio-economic layers to be exploited along with the information layers extracted from Landsat images and field-collected data for physical growth modeling of Karaj city. After generating the required information layers, random forest feature selection method was applied to select the most important variables. Then, the performance of the three modeling methods including multiple logistic regression, and two artificial neural networks, multi-layer perceptron (MLP) and self-organizing map (SOM) were compared using the selected attributes to model the urban physical growth from 2000 to 2010. The results indicated that SOM with overall accuracy of 84.5%, kappa coefficient of 68.9%, ROC of 90.7%, FOM of 43.98% and PCM of 84.5% performed better than the other methods for modelling of urban physical growth. Moreover, the proposed socio-economic attributes combined with the remote sensing-based data were able to improve the performance of the urban physical growth prediction. Finally, cellular automata was applied to predict the Karaj physical growth in 2017 and 2027.
Volume 25, Issue 4 (5-2023)
Abstract
As a tendency of sustainable consumerism, organic food consumption has become a great trend among consumers and one of the unique ones in the global economy. This study aimed to reveal factors affecting consumers’ intention to purchase organic food by using a holistic approach considering behavioral drivers, consumer awareness, and demographic characteristics. Theory of Planned Behavior was used to have a deep understanding of behavioral drivers. Logistic regression analysis was applied to determine the factors affecting consumers' intention to purchase organic food. Behavioral factors were derived by different scales and the suitability of these measurement tools was approved by confirmatory factor analysis. The findings of the study showed that subjective norms, perceived behavioral control, health awareness, social responsibility concern, and trust had a positive influence on individuals' intention to purchase organic food; whereas, subjective attitudes and environmental awareness had no effect. The study produced knowledge on drivers and barriers of organic food consumption that may help all stakeholders of the sector mainly producers, marketers, and policymakers. Results of the study present an integrated model on consumer behavior toward organic food in emerging countries.
Volume 25, Issue 6 (11-2023)
Abstract
Fresh Fruit and Vegetable (FFV) is indispensable for human health, as well as being an economically important sub-sector of agriculture. Especially with the Covid-19 pandemic, the importance given to FFV has increased. The aim of this study was to present the household FFV consumption rate by regions and the factors affecting FFV consumption level. A sample of 720 respondents was selected for online survey from the residents of all cities, in line with the population size of Turkey and the survey study was conducted in 2021. FFV consumption rates were calculated by regions and also ordinal logistic regression model was executed to determine affective factors. The study revealed that the highest FFV consumption rates by region were the Aegean (34.12%), Mediterranean (33.06%) and East Marmara (26.84%), while the lowest consumption rates were Central East Anatolia (18.60%). Also, according to result of Ordinal Logistic Regression (OLR) model, some explanatory variables such as age, marital status, education level and Covid status were found to have a significant effect on consumption level of FFV. The age older, probability of being in high consumption level increases (P< 0.05). Besides, married people's probability of being in high consumption level was higher than single ones (P< 0.01). People having university education level were more likely to be in high consumption level compared to those having primary education level (P< 0.05). People having had Covid-19 were more likely to be in high consumption level compared to those having not been Covid positive (P< 0.01). Individuals who were young, single/divorced, having not university education, or tested negative for Covid-19 should be encouraged to consume more FFV by governments’ health care departments. In addition to informing about the benefits of FFV consumption, FFV food assistance can be provided to these individuals in cash or in kind.
